TopazVideoEnhance - ComfyUI Built-in Node Documentation

The Topaz Video Enhance node uses an external API to improve video quality. It can upscale video resolution, increase frame rate through interpolation, and apply compression. The node processes an input MP4 video and returns an enhanced version based on the selected settings.

Inputs

Parameter	Description	Data Type	Required	Range
`video`	The input video file to be enhanced.	VIDEO	Yes	-
`upscaler_enabled`	Enables or disables the video upscaling feature (default: True).	BOOLEAN	Yes	-
`upscaler_model`	The AI model used for upscaling the video.	COMBO	Yes	`"Starlight (Astra) Fast"` `"Starlight (Astra) Creative"` `"Starlight Precise 2.5"`
`upscaler_resolution`	The target resolution for the upscaled video.	COMBO	Yes	`"FullHD (1080p)"` `"4K (2160p)"`
`upscaler_creativity`	Creativity level (applies only to Starlight (Astra) Creative). (default: “low”)	COMBO	No	`"low"` `"middle"` `"high"`
`interpolation_enabled`	Enables or disables the frame interpolation feature (default: False).	BOOLEAN	No	-
`interpolation_model`	The model used for frame interpolation (default: “apo-8”).	COMBO	No	`"apo-8"`
`interpolation_slowmo`	Slow-motion factor applied to the input video. For example, 2 makes the output twice as slow and doubles the duration. (default: 1)	INT	No	1 to 16
`interpolation_frame_rate`	Output frame rate. (default: 60)	INT	No	15 to 240
`interpolation_duplicate`	Analyze the input for duplicate frames and remove them. (default: False)	BOOLEAN	No	-
`interpolation_duplicate_threshold`	Detection sensitivity for duplicate frames. (default: 0.01)	FLOAT	No	0.001 to 0.1
`dynamic_compression_level`	CQP level. (default: “Low”)	COMBO	No	`"Low"` `"Mid"` `"High"`

Note: At least one enhancement feature must be enabled. The node will raise an error if both upscaler_enabled and interpolation_enabled are set to False. The input video must be in MP4 format.

Outputs

Output Name	Description	Data Type
`video`	The enhanced output video file.	VIDEO

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): ef2d1e62c0000f4d9a99014317db2f1c4e0b8a77334024cf614ec0376058a2f7

​Inputs

​Outputs

Inputs

Outputs